如何使用pdf.js庫呈現整個pdf文檔？

Question

我嘗試使用pdf.js庫渲染PDF文檔。 我只知道javascript的基礎知識並且我是承諾的新手，所以首先我按照這個頁面上的建議： 使用pdf.js和ImageData （ 2。answer）將.pdf渲染到單個Canvas 。
但結果是，我將所有頁面都空白的文檔呈現。 所有的圖片和顏色都很好，但甚至不是一行文字。 我也嘗試了其他一些教程，但要么得到相同的結果，要么文檔完全丟失。 現在，我的代碼看起來像這樣:(它與教程幾乎完全相同）

function loadPDFJS(pid, pageUrl){

    PDFJS.disableWorker = true;
    PDFJS.workerSrc = 'pdfjs/build/pdf.worker.js';

    var canvas = document.createElement('canvas');
    var ctx = canvas.getContext('2d');
    var pages = [];
    var currentPage = 1;

    var url = '/search/nimg/IMG_FULL/' + pid + '#page=1';

    PDFJS.getDocument(url).then(function (pdf) {

        if(currentPage <= pdf.numPages) getPage();

        function getPage() {
            pdf.getPage(currentPage).then(function(page){
                var scale = 1.5;
                var viewport = page.getViewport(scale);

                canvas.height = viewport.height;
                canvas.width = viewport.width;

                var renderContext = {
                    canvasContext: ctx,
                    viewport: viewport
                };

                page.render(renderContext).then(function() {
                    pages.push(canvas.toDataURL());
                    if(currentPage < pdf.numPages) {
                        currentPage++;
                        getPage();
                    } else {
                        done();
                    }
                });
            });
        }
    });

    function done() {
        for(var i = 0; i < pages.length; i++){
            drawPage(i, addPage);
        }
    }

    function addPage(img){
        document.body.appendChild(img);
    }

    function drawPage(index, callback){
        var img = new Image;
        img.onload = function() {
            ctx.drawImage(this, 0, 0, ctx.canvas.width, ctx.canvas.height);
            callback(this);
        }
        img.src = pages[index];
    }
}

Answer 1

謝謝@ user3913960，你的概念對我有用。 我在你修復的代碼中發現了一些問題。 這是代碼：

function loadPDFJS(pageUrl) {
    PDFJS.workerSrc = 'resources/js/pdfjs/pdf.worker.js';
    var currentPage = 1;
    var pages = [];
    var globalPdf = null;
    var container = document.getElementById('pdf-container');
    function renderPage(page) {
        //
        // Prepare canvas using PDF page dimensions
        //
        var canvas = document.createElement('canvas');
        // Link: http://stackoverflow.com/a/13039183/1577396
        // Canvas width should be set to the window's width for appropriate
        // scaling factor of the document with respect to the canvas width
        var viewport = page.getViewport(window.screen.width / page.getViewport(1.0).width);
        // append the created canvas to the container
        container.appendChild(canvas);
        // Get context of the canvas
        var context = canvas.getContext('2d');
        canvas.height = viewport.height;
        canvas.width = viewport.width;
        //
        // Render PDF page into canvas context
        //
        var renderContext = {
            canvasContext: context,
            viewport: viewport
        };
        page.render(renderContext).then(function () {
            if (currentPage < globalPdf.numPages) {
                pages[currentPage] = canvas;
                currentPage++;
                globalPdf.getPage(currentPage).then(renderPage);
            } else {
                // Callback function here, which will trigger when all pages are loaded
            }
        });
    }
    PDFJS.getDocument(pageUrl).then(function (pdf) {
        if(!globalPdf){
            globalPdf = pdf;
        }
        pdf.getPage(currentPage).then(renderPage);
    });
}
loadPDFJS("somepdffilenamehere.pdf");

Answer 2

K所以我再次看了我的代碼，我開始了。 我讓它更簡單，我終於讓它工作了。 現在它看起來像這樣：

var canvasContainer = document.getElementById('pdfImageImg');
function loadPDFJS(pid, pageUrl){

    PDFJS.workerSrc = 'pdfjs/build/pdf.worker.js';

    var currentPage = 1;
    var pages = [];
    var url = '/search/nimg/IMG_FULL/' + pid + '#page=1';

    PDFJS.getDocument(url).then(function(pdf) {
            pdf.getPage(currentPage).then(renderPage);

    function renderPage(page) {
        var height = 700;
        var viewport = page.getViewport(1);
        var scale = height / viewport.height;
        var scaledViewport = page.getViewport(scale);

        var canvas = document.createElement('canvas');
        var context = canvas.getContext('2d');
        canvas.height = scaledViewport.height;
        canvas.width = scaledViewport.width;

        var renderContext = {
            canvasContext: context,
            viewport: scaledViewport
        };
        page.render(renderContext).then(function () {
            if(currentPage < pdf.numPages) {
                pages[currentPage] = canvas;
                currentPage++;
                pdf.getPage(currentPage).then(renderPage);
            } else {
                for (var i = 1; i < pages.length; i++) {
                    document.getElementById('pdfImageImg').appendChild(pages[i]);
                }
            }
        });
    }

    });
}

Answer 3

pdfjs-dist庫包含用於構建PDF查看器的部件。 您可以使用PDFPageView呈現所有頁面。 基於https://github.com/mozilla/pdf.js/blob/master/examples/components/pageviewer.html ：

 var url = "https://cdn.mozilla.net/pdfjs/tracemonkey.pdf"; var container = document.getElementById('container'); // Load document PDFJS.getDocument(url).then(function (doc) { var promise = Promise.resolve(); for (var i = 0; i < doc.numPages; i++) { // One-by-one load pages promise = promise.then(function (id) { return doc.getPage(id + 1).then(function (pdfPage) { // Add div with page view. var SCALE = 1.0; var pdfPageView = new PDFJS.PDFPageView({ container: container, id: id, scale: SCALE, defaultViewport: pdfPage.getViewport(SCALE), // We can enable text/annotations layers, if needed textLayerFactory: new PDFJS.DefaultTextLayerFactory(), annotationLayerFactory: new PDFJS.DefaultAnnotationLayerFactory() }); // Associates the actual page with the view, and drawing it pdfPageView.setPdfPage(pdfPage); return pdfPageView.draw(); }); }.bind(null, i)); } return promise; }); 

 #container > *:not(:first-child) { border-top: solid 1px black; } 

 <link href="https://npmcdn.com/pdfjs-dist/web/pdf_viewer.css" rel="stylesheet"/> <script src="https://npmcdn.com/pdfjs-dist/web/compatibility.js"></script> <script src="https://npmcdn.com/pdfjs-dist/build/pdf.js"></script> <script src="https://npmcdn.com/pdfjs-dist/web/pdf_viewer.js"></script> <div id="container" class="pdfViewer singlePageView"></div> 

另請參見如何使用PDF.JS顯示整個PDF（不僅僅是一頁）？

Answer 4

我使用下面的代碼來呈現包含多個頁面的pdf。

PDFJS.disableWorker = true; // due to CORS
var canvas = document.createElement('canvas'),
ctx = canvas.getContext('2d'),
pages = [],
currentPage = 1,
url = 'your_pdf.pdf';

PDFJS.getDocument(url).then(function(pdf) {
  if (currentPage <= pdf.numPages) getPage();

  // main entry point/function for loop
  function getPage() {
    // when promise is returned do as usual
    pdf.getPage(currentPage).then(function(page) {
      var scale = 1;
      var viewport = page.getViewport(scale);
      canvas.height = viewport.height;
      canvas.width = viewport.width;

      var renderContext = {
        canvasContext: ctx,
        viewport: viewport
      };

      // now, tap into the returned promise from render:
      page.render(renderContext).then(function() {
        // store compressed image data in array
        pages.push(canvas.toDataURL());

        if (currentPage < pdf.numPages) {
          currentPage++;
          getPage(); // get next page
        } else {
          // after all the pages are parsed
          for (var i = 0; i < pages.length; i++) {
            drawPage(i);
          }
        }
      });
    });
  }
});

function drawPage(index, callback) {
  var img = new Image;
  img.onload = function() {
    ctx.drawImage(this, 0, 0, ctx.canvas.width, ctx.canvas.height);
    if (index > 0) img.style.display = 'inline-block';
    document.body.appendChild(img);
  }
  img.src = pages[index]; // start loading the data-uri as source
}